Prediction and Classification of Flood Susceptibility Based on Historic Record in a Large, Diverse, and Data Sparse Country
The emergence of Machine learning (ML) algorithms has shown competency in a variety of fields and are growing in popularity in their application to geospatial science issues. Most recently, and notably, ML algorithms have been applied to flood susceptibility (FS) mapping. Leveraging high-power compu...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Environmental Sciences Proceedings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4931/25/1/18 |
| _version_ | 1797594968930385920 |
|---|---|
| author | Heather McGrath Piper Nora Gohl |
| author_facet | Heather McGrath Piper Nora Gohl |
| author_sort | Heather McGrath |
| collection | DOAJ |
| description | The emergence of Machine learning (ML) algorithms has shown competency in a variety of fields and are growing in popularity in their application to geospatial science issues. Most recently, and notably, ML algorithms have been applied to flood susceptibility (FS) mapping. Leveraging high-power computing systems and existing ML algorithms with national datasets of Canada, this project has explored methods to create a national FS layer across a geographically large and diverse country with limited training data. First, approaches were considered on how to generate a map of FS for Canada at two different levels, (i) national, which combined all training data into one model, and (ii) regional, where multiple models were created, based on regional similarities, and the results were mosaicked to generate a FS map. The second experiment explored the predictive capability of several ML algorithms across the geographically large and diverse landscape. Results indicate that the national approach provides a better prediction of FS, with 95.7% of the test points, 91.5% of the pixels in the training sites, and 89.6% of the pixels across the country correctly predicted as flooded, compared to 65.5%, 80.6% and 75.6%, respectively, in the regional approach. ML models applied across the country found that support vector machine (svmRadial) and Neural Network (nnet) performed poorly in areas away from the training sites, while random forest (parRF) and Multivariate Adaptive Regression Spline (earth) performed better. A national ensemble model was ultimately selected as this blend of models compensated for the biases found in the individual models in geographic areas far removed from training sites. |
| first_indexed | 2024-03-11T02:30:10Z |
| format | Article |
| id | doaj.art-e0c812e2c90a44c182f0de82a1271bfd |
| institution | Directory Open Access Journal |
| issn | 2673-4931 |
| language | English |
| last_indexed | 2024-03-11T02:30:10Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Environmental Sciences Proceedings |
| spelling | doaj.art-e0c812e2c90a44c182f0de82a1271bfd2023-11-18T10:19:12ZengMDPI AGEnvironmental Sciences Proceedings2673-49312023-03-012511810.3390/ECWS-7-14235Prediction and Classification of Flood Susceptibility Based on Historic Record in a Large, Diverse, and Data Sparse CountryHeather McGrath0Piper Nora Gohl1Natural Resources Canada, Ottawa, ON K1A 0E4, CanadaNatural Resources Canada, Ottawa, ON K1A 0E4, CanadaThe emergence of Machine learning (ML) algorithms has shown competency in a variety of fields and are growing in popularity in their application to geospatial science issues. Most recently, and notably, ML algorithms have been applied to flood susceptibility (FS) mapping. Leveraging high-power computing systems and existing ML algorithms with national datasets of Canada, this project has explored methods to create a national FS layer across a geographically large and diverse country with limited training data. First, approaches were considered on how to generate a map of FS for Canada at two different levels, (i) national, which combined all training data into one model, and (ii) regional, where multiple models were created, based on regional similarities, and the results were mosaicked to generate a FS map. The second experiment explored the predictive capability of several ML algorithms across the geographically large and diverse landscape. Results indicate that the national approach provides a better prediction of FS, with 95.7% of the test points, 91.5% of the pixels in the training sites, and 89.6% of the pixels across the country correctly predicted as flooded, compared to 65.5%, 80.6% and 75.6%, respectively, in the regional approach. ML models applied across the country found that support vector machine (svmRadial) and Neural Network (nnet) performed poorly in areas away from the training sites, while random forest (parRF) and Multivariate Adaptive Regression Spline (earth) performed better. A national ensemble model was ultimately selected as this blend of models compensated for the biases found in the individual models in geographic areas far removed from training sites.https://www.mdpi.com/2673-4931/25/1/18flood susceptibilityCanadamachine learningflood priority setting |
| spellingShingle | Heather McGrath Piper Nora Gohl Prediction and Classification of Flood Susceptibility Based on Historic Record in a Large, Diverse, and Data Sparse Country Environmental Sciences Proceedings flood susceptibility Canada machine learning flood priority setting |
| title | Prediction and Classification of Flood Susceptibility Based on Historic Record in a Large, Diverse, and Data Sparse Country |
| title_full | Prediction and Classification of Flood Susceptibility Based on Historic Record in a Large, Diverse, and Data Sparse Country |
| title_fullStr | Prediction and Classification of Flood Susceptibility Based on Historic Record in a Large, Diverse, and Data Sparse Country |
| title_full_unstemmed | Prediction and Classification of Flood Susceptibility Based on Historic Record in a Large, Diverse, and Data Sparse Country |
| title_short | Prediction and Classification of Flood Susceptibility Based on Historic Record in a Large, Diverse, and Data Sparse Country |
| title_sort | prediction and classification of flood susceptibility based on historic record in a large diverse and data sparse country |
| topic | flood susceptibility Canada machine learning flood priority setting |
| url | https://www.mdpi.com/2673-4931/25/1/18 |
| work_keys_str_mv | AT heathermcgrath predictionandclassificationoffloodsusceptibilitybasedonhistoricrecordinalargediverseanddatasparsecountry AT pipernoragohl predictionandclassificationoffloodsusceptibilitybasedonhistoricrecordinalargediverseanddatasparsecountry |